| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 year ago |
|
block.py
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
1 year ago |
|
config.py
|
842912d022
feat: on-the-fly gguf conversion (#250)
|
11 months ago |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
11 months ago |
|
logger.py
|
a3cab09b69
chore: logging env variable
|
11 months ago |
|
logits_processor.py
|
53a9c60442
fix: logit processor declarations and application (#242)
|
11 months ago |
|
outputs.py
|
c0aac15421
feat: S-LoRA support (#222)
|
1 year ago |
|
prefix.py
|
c0aac15421
feat: S-LoRA support (#222)
|
1 year ago |
|
sampling_params.py
|
e75daadfbd
don't copy LogitsProcessors
|
10 months ago |
|
sequence.py
|
d2db4143fa
feat: add grafana for metrics (#240)
|
11 months ago |
|
test_utils.py
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
1 year ago |
|
utils.py
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
11 months ago |
AlpinDale
e75daadfbd
don't copy LogitsProcessors